Finding Evidence of Fraudster Companies in the CEO’s Letter to Shareholders with Sentiment Analysis

Núria Bel,Gabriel Bracons,Sophia Anderberg

doi:10.3390/info12080307

Núria Bel, Gabriel Bracons + Show 1 more

Open Access

https://doi.org/10.3390/info12080307

Copy DOI

Abstract

The goal of our research was to assess whether the observation about deceptive texts having a lower positive tone than truthful ones in terms of sentiment could become operative and be used for building a classifier in the particular case of fraudster’s letters written in Spanish. The data were the letters that CEOs address to company shareholders in their annual financial reports, and the task was to identify the letters of companies that committed financial misconduct or fraud. This case was challenging for two reasons: first, most of the research worked with spontaneous written or spoken texts, while these letters did not; second, most of the research in this area worked on English texts, while we validated the linguistic cues found as evidence of deception for Spanish texts. The results of our research confirm that an SVM trained with a bag-of-words model of frequent adjectives can achieve 81% accuracy because these adjectives bring the information about which positive or negative tone and which word combinations in a text turn out to be a characteristic of fraudster’s texts.

Highlights

We present the results of the application of Sentiment analysis (SA) to letters that CEOs address to Spanish company shareholders in annual financial reports
For refining the results of the classification rule (1), we studied to combine the score with other cues, such as lexical diversity and text length, but with no success in improving the classification results
The aim of our study was to assess to what extent sentiment-related information could be used to identify letters that are from companies that have been involved in financial misconduct or fraud

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Sentiment analysis (SA) is the area of natural language processing that is focused on identifying subjective information, such as the polarity (positive, negative, or neutral) of the writer’s opinion and other manifestations of people’s emotions as expressed in texts [1]

Objectives

Methods

Results

Discussion

Conclusion